576
No AI* Here - A Response to Mozilla's Next Chapter - Waterfox Blog (www.waterfox.com)
submitted 10 months ago by to c/technology@lemmy.world
114 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[+] -51 points 10 months ago (8 children)

Pretty sure they thought of this. But maybe you are the first very smart person ever to think of it, who knows

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 8 child comments
    •
  • [–] 45 points 10 months ago (2 children)

    They have and they've explicitly said it's not solved lmao

    A 1% attack success rate—while a significant improvement—still represents meaningful risk. No browser agent is immune to prompt injection, and we share these findings to demonstrate progress, not to claim the problem is solved

    Mitigating the risk of prompt injections in browser use \ Anthropic - https://www.anthropic.com/research/prompt-injection-defenses

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [+] -20 points 10 months ago (1 child)

    I've used agents, they tell you everything they're going to do. And they're incredibly slow and stupid. I don't think OPs original premise of it instantly and secretly stealing your bank account details is realistic.

    I don't think I said prompt injection didn't exist, just that it didn't need to be worried about by users in exactly the way that was described

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 16 points 10 months ago*

    and these browsers are specifically not that… these browsers are intended to do things like categorise tabs, complete forms, etc automatically without your interaction

    of course they’ll ask before they do things they consider destructive, but what they consider destructive and what a malicious actor can use are very different things

    some of that is certainly benign, but the point with prompt injection is that it can take benign things and make them plausibly malicious

  • permalink
  • fedilink
  • source
  • parent
  • [–] 37 points 10 months ago (4 children)

    It doesn't matter that they've thought of it.

    Dont worry guys, we've thought about viruses, and we've solved viruses now, no more work needs to be done. We'll never have problems with virus again..

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [+] -31 points 10 months ago (4 children)
    [removed by mod]
  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 20 points 10 months ago (3 children)

    Damn, this is a fucking brain dead take. It doesn't even warrant a proper response.

    Its "solved" because of decades of ongoing research and the fact that OS's like Windows have an antivirus built in that regularly get updates.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] 18 points 10 months ago

    There's whole industry to solve this problem and yet there are many millions affected each year meaning it's not even close to being solved. Maybe quite the other way around judging how companies like Google recently said it's a big problem for them.

    The dude above says it themselves: you need to be smart to not fall for some malware(which they are wrong about, there many examples of smart people falling to phishing). Luckily LLMs are perfectly smart and never do stupid shit, right?

  • permalink
  • fedilink
  • source
  • parent
    • load more comments (-1 replies)